Towards Defining an Efficient and Expandable File Format for AI-Generated Contents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Yixin, Feng, Runsen, Li, Xin, Li, Weiping, Chen, Zhibo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912225041580032
author Gao, Yixin
Feng, Runsen
Li, Xin
Li, Weiping
Chen, Zhibo
author_facet Gao, Yixin
Feng, Runsen
Li, Xin
Li, Weiping
Chen, Zhibo
contents Recently, AI-generated content (AIGC) has gained significant traction due to its powerful creation capability. However, the storage and transmission of large amounts of high-quality AIGC images inevitably pose new challenges for recent file formats. To overcome this, we define a new file format for AIGC images, named AIGIF, enabling ultra-low bitrate coding of AIGC images. Unlike compressing AIGC images intuitively with pixel-wise space as existing file formats, AIGIF instead compresses the generation syntax. This raises a crucial question: Which generation syntax elements, e.g., text prompt, device configuration, etc, are necessary for compression/transmission? To answer this question, we systematically investigate the effects of three essential factors: platform, generative model, and data configuration. We experimentally find that a well-designed composable bitstream structure incorporating the above three factors can achieve an impressive compression ratio of even up to 1/10,000 while still ensuring high fidelity. We also introduce an expandable syntax in AIGIF to support the extension of the most advanced generation models to be developed in the future.
format Preprint
id arxiv_https___arxiv_org_abs_2410_09834
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Defining an Efficient and Expandable File Format for AI-Generated Contents
Gao, Yixin
Feng, Runsen
Li, Xin
Li, Weiping
Chen, Zhibo
Computer Vision and Pattern Recognition
Image and Video Processing
Recently, AI-generated content (AIGC) has gained significant traction due to its powerful creation capability. However, the storage and transmission of large amounts of high-quality AIGC images inevitably pose new challenges for recent file formats. To overcome this, we define a new file format for AIGC images, named AIGIF, enabling ultra-low bitrate coding of AIGC images. Unlike compressing AIGC images intuitively with pixel-wise space as existing file formats, AIGIF instead compresses the generation syntax. This raises a crucial question: Which generation syntax elements, e.g., text prompt, device configuration, etc, are necessary for compression/transmission? To answer this question, we systematically investigate the effects of three essential factors: platform, generative model, and data configuration. We experimentally find that a well-designed composable bitstream structure incorporating the above three factors can achieve an impressive compression ratio of even up to 1/10,000 while still ensuring high fidelity. We also introduce an expandable syntax in AIGIF to support the extension of the most advanced generation models to be developed in the future.
title Towards Defining an Efficient and Expandable File Format for AI-Generated Contents
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2410.09834